© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 744
    Prev
    Next
    INDEX
    Explanations

    entities and actions related to family relationships and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    possessive pronouns and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.93
    !*\
    -0.82
    Tembelea
    -0.82
    ConstraintMaker
    -0.79
     Normdatei
    -0.78
     estekak
    -0.77
     EconPapers
    -0.76
    TagMode
    -0.76
    arrol
    -0.75
     ویکی‌پدیا
    -0.73
    POSITIVE LOGITS
     your
    0.83
    对方的
    0.76
     hennes
    0.73
     YOUR
    0.70
    your
    0.65
     my
    0.64
     peoples
    0.64
     jūsų
    0.62
     Your
    0.62
    您的
    0.62
    Activations Density 0.551%

    No Known Activations